phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove /v1/inference/completion and implementations

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 03:46:07 -04:00
parent 606f4cf281
commit 4b641d7127
78 changed files with 16143 additions and 17755 deletions
Download patch file Download diff file Expand all files Collapse all files

72
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -103,8 +103,6 @@ from llama_stack.apis.inference import (
JsonSchemaResponseFormat,
Message,
OpenAIChatCompletion,
OpenAICompletion,
OpenAICompletionChoice,
OpenAIEmbeddingData,
OpenAIMessageParam,
OpenAIResponseFormatParam,
@ -1281,76 +1279,6 @@ async def prepare_openai_completion_params(**params):
return completion_params
class OpenAICompletionToLlamaStackMixin:
async def openai_completion(
self,
model: str,
prompt: str | list[str] | list[int] | list[list[int]],
best_of: int | None = None,
echo: bool | None = None,
frequency_penalty: float | None = None,
logit_bias: dict[str, float] | None = None,
logprobs: bool | None = None,
max_tokens: int | None = None,
n: int | None = None,
presence_penalty: float | None = None,
seed: int | None = None,
stop: str | list[str] | None = None,
stream: bool | None = None,
stream_options: dict[str, Any] | None = None,
temperature: float | None = None,
top_p: float | None = None,
user: str | None = None,
guided_choice: list[str] | None = None,
prompt_logprobs: int | None = None,
suffix: str | None = None,
) -> OpenAICompletion:
if stream:
raise ValueError(f"{self.__class__.__name__} doesn't support streaming openai completions")
# This is a pretty hacky way to do emulate completions -
# basically just de-batches them...
prompts = [prompt] if not isinstance(prompt, list) else prompt
sampling_params = _convert_openai_sampling_params(
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
)
choices = []
# "n" is the number of completions to generate per prompt
n = n or 1
for _i in range(0, n):
# and we may have multiple prompts, if batching was used
for prompt in prompts:
result = self.completion(
model_id=model,
content=prompt,
sampling_params=sampling_params,
)
index = len(choices)
text = result.content
finish_reason = _convert_stop_reason_to_openai_finish_reason(result.stop_reason)
choice = OpenAICompletionChoice(
index=index,
text=text,
finish_reason=finish_reason,
)
choices.append(choice)
return OpenAICompletion(
id=f"cmpl-{uuid.uuid4()}",
choices=choices,
created=int(time.time()),
model=model,
object="text_completion",
)
class OpenAIChatCompletionToLlamaStackMixin:
async def openai_chat_completion(
self,